Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jury
    -0.07
     нею
    -0.07
    _L
    -0.07
     cycle
    -0.07
     Geoffrey
    -0.07
    (status
    -0.06
    .lesson
    -0.06
     حف
    -0.06
    igger
    -0.06
     jurors
    -0.06
    POSITIVE LOGITS
     Wheat
    0.06
    xlsx
    0.06
     Libre
    0.06
    ài
    0.06
    ULT
    0.06
     phot
    0.06
    uint
    0.06
    兄
    0.05
     ve
    0.05
    istributions
    0.05
    Act Density 0.011%

    No Known Activations